© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4856
    Prev
    Next
    INDEX
    Explanations

    the word "worth" along with the modifiers around it but may also activate on the word "value"

    oai_token-act-pair · gemini-2.0-flash

    the concept of value or worth

    np_token-act-pair-logits · gpt-4o-mini

    worth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.73
    IntoConstraints
    -0.57
     cherchés
    -0.56
    RTHOOK
    -0.54
    WriteTagHelper
    -0.54
    KommentareTeilen
    -0.53
     برانيه
    -0.51
    Бахар
    -0.49
    ConstraintMaker
    -0.49
    pushFollow
    -0.49
    POSITIVE LOGITS
     Nowy
    0.62
     Esperanto
    0.60
     every
    0.58
    heritance
    0.57
     ciudadana
    0.56
     opting
    0.56
     shutting
    0.55
     regaining
    0.55
     conveyance
    0.55
    商品説明
    0.55
    Activations Density 2.798%

    No Known Activations